arXiv Machine Learning July 22, 2026 By Fabian A Mikulasch, Friedemann Zenke

Understanding Self-Supervised Learning via Latent Distribution Matching

Read the original on arXiv Machine Learning →

arXiv:2605. 03517v4 Announce Type: replace Abstract: Self-supervised learning (SSL) excels at finding general-purpose latent representations from complex data, yet lacks a unifying theoretical framework that explains the diverse existing methods and guides the design of new ones.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

safety

arXiv Machine Learning

Jun 2

Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\"om Approximation

arXiv:2509. 24467v3 Announce Type: replace Abstract: Self-supervised learning (SSL) learns representations from massive unlabeled data, yet the resulting models typically operate as black boxes, necessitating domain-specific explanations.

By Maedeh Zarvandi, Michael Timothy, Theresa Wasserer, Debarghya Ghoshdastidar

diffusion benchmarks safety

arXiv AI

Jul 22

RAMP: Recognition parametrisation by Amortised Message Passing

arXiv:2607. 18883v1 Announce Type: cross Abstract: A central aim of unsupervised learning is to uncover latent factors that explain dependencies among observations.

By Lior Fox, Kai Biegun, James Heald, Samo Hromadka, Arielle Rosinski, Maneesh Sahani

arXiv AI

Jun 12

Two-Layer Linear Auto-Regressive Models Estimate Latent States

arXiv:2606. 12691v1 Announce Type: cross Abstract: Auto-regressive models have emerged as powerful tools for sequential data, from language to video.

By Yahya Sattar, Sunmook Choi, Leo Maynard-Zhang, Yassir Jedra, Maryam Fazel, Sarah Dean

arXiv Machine Learning

Jul 7

Self-Supervised Learning from Structural Invariance

arXiv:2602. 02381v2 Announce Type: replace Abstract: Joint-embedding self-supervised learning (SSL), the key paradigm for unsupervised representation learning from visual data, learns from invariances between semantically-related data pairs.

By Yipeng Zhang, Hafez Ghaemi, Jungyoon Lee, Shahab Bakhtiari, Eilif B. Muller, Laurent Charlin

rag efficiency

arXiv Machine Learning

Aug 11

A solvable high-dimensional model where nonlinear autoencoders learn structure invisible to PCA while test loss misaligns with generalization

arXiv:2602. 10680v2 Announce Type: replace-cross Abstract: Many real-world datasets contain hidden structure that cannot be detected by simple linear correlations between input features.

By Vicente Conde Mendes, Lorenzo Bardone, C\'edric Koller, Jorge Medina Moreira, Vittorio Erba, Emanuele Troiani, Lenka Zdeborov\'a

arXiv Machine Learning

Jul 24

Generative Bayesian Filtering for State Estimation

arXiv:2607. 20521v1 Announce Type: new Abstract: The state of a dynamic system evolves over time, switching among several latent modes that govern its observable behavior.

By Lei Cao, Sihang Feng, Jixin Yan, Tao Sun, Naichen Shi

Related stories

Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\"om Approximation

RAMP: Recognition parametrisation by Amortised Message Passing

Two-Layer Linear Auto-Regressive Models Estimate Latent States

Self-Supervised Learning from Structural Invariance

A solvable high-dimensional model where nonlinear autoencoders learn structure invisible to PCA while test loss misaligns with generalization

Generative Bayesian Filtering for State Estimation